Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JUST
    -0.07
    Descri
    -0.07
    COL
    -0.07
    _UC
    -0.06
    SEQ
    -0.06
     �
    -0.06
     Але
    -0.06
     concert
    -0.06
     але
    -0.06
     piping
    -0.06
    POSITIVE LOGITS
    aneous
    0.07
    асс
    0.07
    erved
    0.07
    .energy
    0.06
    reed
    0.06
    :')
    0.06
     �
    0.06
    erv
    0.06
    iv
    0.06
     expansions
    0.06
    Act Density 0.081%

    No Known Activations